nextjs-react

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to fetch external documentation using WebSearch and WebFetch to ensure it uses the latest standards.
  • Ingestion points: Documentation is fetched from nextjs.org, saleor.io, and github.com/saleor via SKILL.md.
  • Boundary markers: None explicitly defined in the fetching instructions.
  • Capability inventory: The skill has access to Write, Edit, and Bash tools to modify the local environment.
  • Sanitization: None specified for the fetched content.
  • Context: The ingestion is targeted at well-known, high-authority documentation sources, which is a standard operational pattern for this type of technical guidance skill.
  • [EXTERNAL_DOWNLOADS]: The skill recommends the installation of several standard packages from the Node.js ecosystem using npm.
  • Evidence: Recommended packages include @saleor/macaw-ui, @urql/core, @urql/next, graphql, @apollo/client, and tailwindcss. These are established libraries within the React and Saleor development communities.
  • [CREDENTIALS_UNSAFE]: The documentation includes a section on environment variables with architectural guidance on secret management.
  • Evidence: It correctly distinguishes between public variables (NEXT_PUBLIC_SALEOR_API_URL) and server-side secrets (SALEOR_APP_TOKEN), explicitly advising that secrets should remain server-only. No hardcoded credentials or private keys were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 06:33 PM